Finding the optimal exploration-exploitation trade-off online through Bayesian risk estimation and minimization

Recommendations

scientific article; zbMATH DE number 1907146
Learning to optimize via posterior sampling
Bayesian Reinforcement Learning with Exploration
Learning to optimize via information-directed sampling
Optimal online learning for nonlinear belief models using discrete priors

Cites work

10.1162/153244303765208377
A comprehensive survey on safe reinforcement learning
A Knowledge-Gradient Policy for Sequential Information Collection
Adaptive submodularity: theory and applications in active learning and stochastic optimization
An analysis of approximations for maximizing submodular set functions—I
Asymptotic methods in statistical decision theory
Bandit algorithms
Bayesian look ahead one-stage sampling allocations for selection of the best population
Bayesian reinforcement learning: a survey
Congresso internazionale dei matematici. Argomenti delle communicazioni. 3-10 settembre 1928.
Discrete Convex Analysis
Efficient global optimization of expensive black-box functions
Finite-time analysis for the knowledge-gradient policy
Finite-time analysis of the multiarmed bandit problem
scientific article; zbMATH DE number 3128787 (Why is no real title available?)
scientific article; zbMATH DE number 2107164 (Why is no real title available?)
scientific article; zbMATH DE number 3334700 (Why is no real title available?)
Learning to optimize via information-directed sampling
Learning to optimize via posterior sampling
Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges
Near-optimal regret bounds for reinforcement learning
On multi-armed bandit designs for dose-finding trials
On Stochastic Limit and Order Relationships
On the likelihood that one unkrown probability exeeds another in view of the evidence of two samples.
Partial monitoring -- classification, regret bounds, and algorithms
Planning and acting in partially observable stochastic domains
Pure exploration in multi-armed bandits problems
Regret bounds and minimax policies under partial monitoring
Reinforcement Learning, Bit by Bit
Risk-sensitive reinforcement learning
Scalable and efficient Bayes-adaptive reinforcement learning based on Monte-Carlo tree search
Simple Bayesian algorithms for best-arm identification
Technical note -- A note on the equivalence of upper confidence bounds and Gittins indices for patient agents
The knowledge gradient algorithm for a general class of online learning problems
The knowledge-gradient policy for correlated normal beliefs

This page was built for publication: Finding the optimal exploration-exploitation trade-off online through Bayesian risk estimation and minimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6566614)